COVID 19 Mutations

Cartesian tree

Photo by Jr Korpa on Unsplash

It’s clear that there’s a lot of human wood out there for this coronavirus forest fire to burn…
— Michael Thomas Osterholm

Ingest

the tree of mutations

# Tree data
df_tree_path <- "archetypes/covid-19-mutations/covid-19-mutations-tree.csv"
df_tree <- read.csv(df_tree_path, header = TRUE, stringsAsFactors = FALSE)
df_tree

Wrangle

create graph structure

# transform to graph data structure
df_graph <- graph_from_data_frame( df_tree )
df_graph_directed <- graph_from_data_frame( df_tree, directed = TRUE )
df_graph_undirected <- graph_from_data_frame( df_tree, directed = FALSE )

# to view results as data frame
df_graph_view <-  get.data.frame(df_graph, what= "both" ) # as.data.frame(get.edgelist(df_graph))
# df_graph_view

Analytics

compute layouts

# igraph layouts

# bipartite <- create_layout(df_graph, layout = 'igraph', algorithm = 'bipartite')
circle <- create_layout(df_graph, layout = 'igraph', algorithm = 'circle')
dh <- create_layout(df_graph, layout = 'igraph', algorithm = 'dh')
drl <- create_layout(df_graph, layout = 'igraph', algorithm = 'drl')
fr <- create_layout(df_graph, layout = 'igraph', algorithm = 'fr')
gem <- create_layout(df_graph, layout = 'igraph', algorithm = 'gem')
graphopt <- create_layout(df_graph, layout = 'igraph', algorithm = 'graphopt')
grid <- create_layout(df_graph, layout = 'igraph', algorithm = 'grid')
kk <- create_layout(df_graph, layout = 'igraph', algorithm = 'kk')
lgl <- create_layout(df_graph, layout = 'igraph', algorithm = 'lgl')
mds <- create_layout(df_graph, layout = 'igraph', algorithm = 'mds')
nicely <- create_layout(df_graph, layout = 'igraph', algorithm = 'nicely')
sphere <- create_layout(df_graph, layout = 'igraph', algorithm = 'sphere')
star <- create_layout(df_graph, layout = 'igraph', algorithm = 'star')
sugiyama <- create_layout(df_graph, layout = 'igraph', algorithm = 'sugiyama')

# ggraph layouts

backbone <- create_layout(df_graph_undirected, layout = 'backbone')

centrality_bc <- betweenness(df_graph_directed)
centrality_cc <- closeness(df_graph_directed)
centrality <- create_layout(df_graph_undirected, layout = 'centrality', centrality = centrality_bc)

circlepack <- create_layout(df_graph_directed, layout = 'circlepack')
dendrogram <- create_layout(df_graph_directed, layout = 'dendrogram')
eigen <- create_layout(df_graph, layout = 'eigen', type = "laplacian", eigenvector = "smallest")

# fabric <- create_layout(cg, layout = 'fabric')
focus <- create_layout(df_graph_directed, layout = 'focus', focus = 1)

# hive <- create_layout(df_graph, layout = 'hive', axis = friends, sort.by = degree)

linear <- create_layout(df_graph, layout = 'linear')
matrix <- create_layout(df_graph, layout = 'matrix')
partition <- create_layout(df_graph_directed, layout = 'partition')

pmds_pivots <- 3
pmds <- create_layout(df_graph, layout = 'pmds', pivots = pmds_pivots)

stress <- create_layout(df_graph, layout = 'stress')
sunburst <- create_layout(df_graph_directed, layout = 'partition', circular = TRUE)
treemap <- create_layout(df_graph_directed, layout = 'treemap')

# df_unrooted <- df_graph_undirected %>%  activate(edges) %>%  mutate(length = runif(n()))
unrooted <- create_layout(df_graph_undirected, layout = 'unrooted' )

Plot

dendrogram

theme_opts <- theme(
    text = element_text(family = "inconsolata"), 
    plot.margin = unit(c(1.5,1,1,1), "in"),
    legend.position='none'
)

category_palette <- c("Top 100" = "#FFFFFF", "LEAF" = "#FFFFFF", "Creativity" = "#E8F5E9", "Identity" = "#E3F2FD", "Knowledge" = "#F3E5F5","Leadership" = "#FCE4EC")

v1 <- ggraph(df_graph, layout = dendrogram) + 
  # geom_edge_elbow(aes(label = LABEL), angle_calc = 'along', label_dodge = unit(2.5, 'mm')) + 
  # geom_edge_bend(aes(label = LABEL)) +
  geom_edge_diagonal(aes(label = LABEL)) +
  geom_node_point(size=4) +
  geom_node_label( aes(label=name), repel = FALSE, vjust = 0.0, nudge_y = 0.1, size = 6, family = "inconsolata") +
  # coord_fixed(clip = 'off') + 
  theme_void() +
  theme_opts

girafe(ggobj = v1, width_svg = 1280/72, height_svg = 720/72,
       options = list(opts_sizing(rescale = TRUE, width = 1.0))
)

# pg <- ggplot_build(v1)
# pg$data[[2]]
# pg$data[[3]]

sugiyama

v2 <- ggraph(df_graph, layout = sugiyama) + 
  # geom_edge_elbow(aes(label = LABEL), angle_calc = 'along', label_dodge = unit(2.5, 'mm')) + 
  # geom_edge_bend(aes(label = LABEL)) +
  geom_edge_diagonal(aes(label = LABEL)) +
  geom_node_point(size=4) +
  geom_node_label( aes(label=name), repel = FALSE, vjust = 0.0, nudge_y = 0.1, size = 6, family = "inconsolata") +
  # coord_fixed(clip = 'off') + 
  theme_void() +
  theme_opts

girafe(ggobj = v2, width_svg = 1280/72, height_svg = 720/72,
       options = list(opts_sizing(rescale = TRUE, width = 1.0))
)

gem

v3 <- ggraph(df_graph, layout = gem) + 
  # geom_edge_elbow(aes(label = LABEL), angle_calc = 'along', label_dodge = unit(2.5, 'mm')) + 
  # geom_edge_bend(aes(label = LABEL)) +
  geom_edge_diagonal(aes(label = LABEL)) +
  geom_node_point(size=4) +
  geom_node_label( aes(label=name), repel = FALSE, vjust = 0.0, nudge_y = 0.1, size = 6, family = "inconsolata") +
  # coord_fixed(clip = 'off') + 
  theme_void() +
  theme_opts

girafe(ggobj = v3, width_svg = 1280/72, height_svg = 720/72,
       options = list(opts_sizing(rescale = TRUE, width = 1.0))
)

unrooted

v4 <- ggraph(df_graph, layout = unrooted) + 
  # geom_edge_elbow(aes(label = LABEL), angle_calc = 'along', label_dodge = unit(2.5, 'mm')) + 
  # geom_edge_bend(aes(label = LABEL)) +
  geom_edge_diagonal(aes(label = LABEL)) +
  geom_node_point(size=4) +
  geom_node_label( aes(label=name), repel = FALSE, vjust = 0.0, nudge_y = 0.1, size = 6, family = "inconsolata") +
  # coord_fixed(clip = 'off') + 
  theme_void() +
  theme_opts

girafe(ggobj = v4, width_svg = 1280/72, height_svg = 720/72,
       options = list(opts_sizing(rescale = TRUE, width = 1.0))
)

References

citations for narrative and data sources

Narrative: Economist, It’s a family affair, https://www.economist.com/graphic-detail/2021/02/27/the-same-covid-19-mutations-are-appearing-in-different-places
Narrative: Nextstrain, Genomic epidemiology of novel coronavirus, https://nextstrain.org/ncov/gisaid/global
Data sources: Nextstrain, SARS-CoV-2 data, https://github.com/nextstrain/ncov